Knowledge discovery and knowledge transfer in board-level functional fault diagnosis. Ye, F., Zhang, Z., Chakrabarty, K., & Gu, X. In 2014 International Test Conference, pages 1–10, October, 2014. ISSN: 2378-2250doi abstract bibtex Diagnosis of functional failures at the board level is critical for improving product yield and reducing manufacturing cost. Reasoning techniques increase the accuracy of functional-fault diagnosis based on the history of successfully repaired boards. However, depending on the complexity of the product, it usually takes several months to accumulate an adequate database for training a reasoning-based diagnosis system. During the initial product ramp-up phase, reasoning-based diagnosis is not feasible for yield learning, since the required database is not available due to lack of volume. We propose a knowledge-discovery method and a knowledge-transfer method for facilitating board-level functional fault diagnosis. First, an analysis technique based on machine learning is used to discover knowledge from syndromes, which can be used for training a diagnosis engine. Second, knowledge from diagnosis engines used for earlier-generation products can be automatically transferred through root-cause mapping and syndrome mapping based on keywords and board-structure similarities. Two complex boards in volume production and with a mature diagnosis system, and three new boards in the ramp-up phase, are used to validate the proposed knowledge-discovery and knowledge-transfer approach in terms of the diagnosis accuracy obtained using the new diagnosis systems.
@inproceedings{ye_knowledge_2014,
title = {Knowledge discovery and knowledge transfer in board-level functional fault diagnosis},
doi = {10.1109/TEST.2014.7035335},
abstract = {Diagnosis of functional failures at the board level is critical for improving product yield and reducing manufacturing cost. Reasoning techniques increase the accuracy of functional-fault diagnosis based on the history of successfully repaired boards. However, depending on the complexity of the product, it usually takes several months to accumulate an adequate database for training a reasoning-based diagnosis system. During the initial product ramp-up phase, reasoning-based diagnosis is not feasible for yield learning, since the required database is not available due to lack of volume. We propose a knowledge-discovery method and a knowledge-transfer method for facilitating board-level functional fault diagnosis. First, an analysis technique based on machine learning is used to discover knowledge from syndromes, which can be used for training a diagnosis engine. Second, knowledge from diagnosis engines used for earlier-generation products can be automatically transferred through root-cause mapping and syndrome mapping based on keywords and board-structure similarities. Two complex boards in volume production and with a mature diagnosis system, and three new boards in the ramp-up phase, are used to validate the proposed knowledge-discovery and knowledge-transfer approach in terms of the diagnosis accuracy obtained using the new diagnosis systems.},
booktitle = {2014 {International} {Test} {Conference}},
author = {Ye, Fangming and Zhang, Zhaobo and Chakrabarty, Krishnendu and Gu, Xinli},
month = oct,
year = {2014},
note = {ISSN: 2378-2250},
keywords = {Application specific integrated circuits, Engines, Knowledge acquisition, Knowledge discovery, Knowledge transfer, Production, Training, board repair, board-level functional fault diagnosis, data mining, diagnosis engine, earlier-generation product, failure analysis, fault diagnosis, integrated circuit reliability, integrated circuit yield, knowledge discovery method, knowledge transfer method, machine learning, manufacturing cost reduction, printed circuits, product ramp-up phase, product yield, reasoning technique, reasoning-based diagnosis system, root-cause mapping, syndrome mapping, yield learning},
pages = {1--10},
}
Downloads: 0
{"_id":"SLbuZr63yMfaziZTJ","bibbaseid":"ye-zhang-chakrabarty-gu-knowledgediscoveryandknowledgetransferinboardlevelfunctionalfaultdiagnosis-2014","author_short":["Ye, F.","Zhang, Z.","Chakrabarty, K.","Gu, X."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Knowledge discovery and knowledge transfer in board-level functional fault diagnosis","doi":"10.1109/TEST.2014.7035335","abstract":"Diagnosis of functional failures at the board level is critical for improving product yield and reducing manufacturing cost. Reasoning techniques increase the accuracy of functional-fault diagnosis based on the history of successfully repaired boards. However, depending on the complexity of the product, it usually takes several months to accumulate an adequate database for training a reasoning-based diagnosis system. During the initial product ramp-up phase, reasoning-based diagnosis is not feasible for yield learning, since the required database is not available due to lack of volume. We propose a knowledge-discovery method and a knowledge-transfer method for facilitating board-level functional fault diagnosis. First, an analysis technique based on machine learning is used to discover knowledge from syndromes, which can be used for training a diagnosis engine. Second, knowledge from diagnosis engines used for earlier-generation products can be automatically transferred through root-cause mapping and syndrome mapping based on keywords and board-structure similarities. Two complex boards in volume production and with a mature diagnosis system, and three new boards in the ramp-up phase, are used to validate the proposed knowledge-discovery and knowledge-transfer approach in terms of the diagnosis accuracy obtained using the new diagnosis systems.","booktitle":"2014 International Test Conference","author":[{"propositions":[],"lastnames":["Ye"],"firstnames":["Fangming"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Zhaobo"],"suffixes":[]},{"propositions":[],"lastnames":["Chakrabarty"],"firstnames":["Krishnendu"],"suffixes":[]},{"propositions":[],"lastnames":["Gu"],"firstnames":["Xinli"],"suffixes":[]}],"month":"October","year":"2014","note":"ISSN: 2378-2250","keywords":"Application specific integrated circuits, Engines, Knowledge acquisition, Knowledge discovery, Knowledge transfer, Production, Training, board repair, board-level functional fault diagnosis, data mining, diagnosis engine, earlier-generation product, failure analysis, fault diagnosis, integrated circuit reliability, integrated circuit yield, knowledge discovery method, knowledge transfer method, machine learning, manufacturing cost reduction, printed circuits, product ramp-up phase, product yield, reasoning technique, reasoning-based diagnosis system, root-cause mapping, syndrome mapping, yield learning","pages":"1–10","bibtex":"@inproceedings{ye_knowledge_2014,\n\ttitle = {Knowledge discovery and knowledge transfer in board-level functional fault diagnosis},\n\tdoi = {10.1109/TEST.2014.7035335},\n\tabstract = {Diagnosis of functional failures at the board level is critical for improving product yield and reducing manufacturing cost. Reasoning techniques increase the accuracy of functional-fault diagnosis based on the history of successfully repaired boards. However, depending on the complexity of the product, it usually takes several months to accumulate an adequate database for training a reasoning-based diagnosis system. During the initial product ramp-up phase, reasoning-based diagnosis is not feasible for yield learning, since the required database is not available due to lack of volume. We propose a knowledge-discovery method and a knowledge-transfer method for facilitating board-level functional fault diagnosis. First, an analysis technique based on machine learning is used to discover knowledge from syndromes, which can be used for training a diagnosis engine. Second, knowledge from diagnosis engines used for earlier-generation products can be automatically transferred through root-cause mapping and syndrome mapping based on keywords and board-structure similarities. Two complex boards in volume production and with a mature diagnosis system, and three new boards in the ramp-up phase, are used to validate the proposed knowledge-discovery and knowledge-transfer approach in terms of the diagnosis accuracy obtained using the new diagnosis systems.},\n\tbooktitle = {2014 {International} {Test} {Conference}},\n\tauthor = {Ye, Fangming and Zhang, Zhaobo and Chakrabarty, Krishnendu and Gu, Xinli},\n\tmonth = oct,\n\tyear = {2014},\n\tnote = {ISSN: 2378-2250},\n\tkeywords = {Application specific integrated circuits, Engines, Knowledge acquisition, Knowledge discovery, Knowledge transfer, Production, Training, board repair, board-level functional fault diagnosis, data mining, diagnosis engine, earlier-generation product, failure analysis, fault diagnosis, integrated circuit reliability, integrated circuit yield, knowledge discovery method, knowledge transfer method, machine learning, manufacturing cost reduction, printed circuits, product ramp-up phase, product yield, reasoning technique, reasoning-based diagnosis system, root-cause mapping, syndrome mapping, yield learning},\n\tpages = {1--10},\n}\n\n","author_short":["Ye, F.","Zhang, Z.","Chakrabarty, K.","Gu, X."],"key":"ye_knowledge_2014-1","id":"ye_knowledge_2014-1","bibbaseid":"ye-zhang-chakrabarty-gu-knowledgediscoveryandknowledgetransferinboardlevelfunctionalfaultdiagnosis-2014","role":"author","urls":{},"keyword":["Application specific integrated circuits","Engines","Knowledge acquisition","Knowledge discovery","Knowledge transfer","Production","Training","board repair","board-level functional fault diagnosis","data mining","diagnosis engine","earlier-generation product","failure analysis","fault diagnosis","integrated circuit reliability","integrated circuit yield","knowledge discovery method","knowledge transfer method","machine learning","manufacturing cost reduction","printed circuits","product ramp-up phase","product yield","reasoning technique","reasoning-based diagnosis system","root-cause mapping","syndrome mapping","yield learning"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/bxt101","dataSources":["Wsv2bQ4jPuc7qme8R"],"keywords":["application specific integrated circuits","engines","knowledge acquisition","knowledge discovery","knowledge transfer","production","training","board repair","board-level functional fault diagnosis","data mining","diagnosis engine","earlier-generation product","failure analysis","fault diagnosis","integrated circuit reliability","integrated circuit yield","knowledge discovery method","knowledge transfer method","machine learning","manufacturing cost reduction","printed circuits","product ramp-up phase","product yield","reasoning technique","reasoning-based diagnosis system","root-cause mapping","syndrome mapping","yield learning"],"search_terms":["knowledge","discovery","knowledge","transfer","board","level","functional","fault","diagnosis","ye","zhang","chakrabarty","gu"],"title":"Knowledge discovery and knowledge transfer in board-level functional fault diagnosis","year":2014}